What is the industrial IoT solution based on FPGA?

With the gradual disappearance of the Internet dividend, the Internet of Things has followed the trend of the overall technological development and has become a generally optimistic direction for the development of a new generation of industry.

Among them, the application of the Internet of Things in industry is called the Industrial Internet of Things. The Industrial Internet of Things will continuously integrate various types of acquisition or control sensors or controllers with sensing and monitoring capabilities, as well as ubiquitous technology, mobile communication, intelligent analysis and other technologies. To all links of the industrial production process, which greatly improves manufacturing efficiency, improves product quality, reduces product costs and resource consumption, and finally realizes the promotion of traditional industry to a new stage of intelligence. The Industrial Internet of Things is essentially machine-to-machine (M2M) support that extends to the cloud.

At present, the Industrial Internet of Things is still in the early stage of development, but due to its broad application prospects and huge revenue potential, many companies and organizations have invested heavily in the Industrial Internet of Things.

Achronix Semiconductor is one of them. Alok Sanghavi, senior product marketing manager of Achronix Semiconductor, was interviewed by NANDI on topics related to the Industrial Internet of Things. Achronix believes that the Industrial Internet of Things (IIoT) is the new driving force of the global economy. The Industrial Internet of Things not only means communication connections between machines, tools, automation systems, control systems, and even operation support systems such as ERP systems running in local data centers or clouds. At the same time, the Industrial Internet of Things has added and redistributed intelligence in applications such as smart factories, energy production and management, business and building automation, smart logistics and asset tracking, process automation, and smart agriculture. Therefore, connectivity and intelligence are two features included in the Industrial Internet of Things.

These industrial IoT markets have some common characteristics. First, many standards and protocols in these areas have not yet been determined; second, new technologies such as artificial intelligence or edge computing are still in the early stages of adoption in these areas; third, new artificial intelligence or edge computing accompanying the Industrial Internet of Things Both require advanced hardware acceleration.

Alok told reporters from non-net that Achronix believes that with its programmability and flexibility, various FPGA products will play a key role in the new economy driven by the Industrial Internet of Things. Computing power is also particularly important. Special resources such as embedded FPGA (eFPGA) applied in ASIC or SoC will add super hardware acceleration to the system, such as AchronixSpeedcoreGen4 embedded FPGA semiconductor intellectual property (eFPGAIP) machine learning processor (MLP) and other special designs.

Therefore, Achronix's strategy is to exclusively provide customers with a new and most complete FPGA product portfolio, including independent FPGA chips, SiP package chip (chiplet) manufacturing services based on FPGA die, and embedded FPGA semiconductor intellectual property (eFPGAIP ) To help customers or their partners smoothly upgrade the efficiency and capabilities of their chips without significantly changing their algorithms and development environment.

Alok went on to say that for the Industrial Internet of Things (IIoT), connectivity and computing are like two sides of the same coin. With the support of connectivity technologies including wireless and wired solutions, edge computing and cloud computing will become important technologies for industrial IoT applications. Achronix's high-performance and high-density FPGA chips, SiP chiplets based on FPGA die and eFPGAIP provide strong support for both areas of the Industrial Internet of Things.

In the field of communication and connection, there are many new standards and communication protocols constantly emerging, such as 5G is entering the factory floor. Therefore, continuous sensor data needs to be transmitted and converted between different protocols and standards including emerging protocols, traditional protocols, and private protocols. FPGAs have historical advantages in this regard. With the emergence of new communication protocols, FPGA chips and SoC/ASIC with eFPGAIP will continue to serve these markets.

In another area, edge computing and related artificial intelligence technologies are increasingly deployed in different networks. For example, the application range of artificial intelligence in factories has expanded from machine vision-based part quality inspection to sensor fusion and predictive maintenance. The wider application of these technologies has brought new challenges to traditional ASIC methods; and edge intelligence in the Industrial Internet of Things requires hardware acceleration to achieve low-latency data processing.

Therefore, new devices need to have reprogrammability to cope with the evolution of standards or protocols, and/or new algorithms for artificial intelligence and other embedded intelligence. They require the introduction of new architectural innovations in SoCs designed for smart factories and many other applications. Chip designers should focus on embedded FPGA (eFPGA) IP products with second-level acceleration, such as SpeedcoreGen4eFPGAIP in Achronix The machine learning processor (MLP) in the system can improve the performance of related processing such as artificial intelligence/machine learning by 300%.

FPGA in edge computing

For the specific role of edge computing in the Industrial Internet of Things, Alok added that for many industries, edge computing is a very important trend. Therefore, all stakeholders, including factory owners, equipment manufacturers, system integrators, software vendors, and related chip designers, must have a vision for their hardware acceleration infrastructure. They should choose a hardware infrastructure that is flexible and extensible, and be able to migrate or evolve from standard devices to SoCs that ultimately target category applications without the need for architectural changes to their edge computing solutions. Achronix provides a complete set of FPGA-based solutions for edge computing.

For example, an industrial IoT solution provider can initially choose Achronix's independent FPGA chip to develop algorithms and start quickly. Later, they can obtain FPGA chip die and system-in-package (SiP) services from Achronix to manufacture their own SiP multi-die chips, where the FPGA device is directly connected to the processor and/or other devices, so that Get higher performance. When the demand for devices with artificial intelligence capabilities is increasing, and they need more computing power to support a set of smart factory functions, they can use AchronixSpeedcoreGen4eFPGA semiconductor intellectual property (IP) to develop a system-level chip ( SoC), so that you can get the highest price-performance ratio more directly for the application.

If you want to know more, our website has product specifications for FPGA development, you can go to ALLICDATA ELECTRONICS LIMITED to get more information